Fraud Detection in Banking: A Machine Learning Approach using Credit Card Transaction Data

Abstract

Financial fraud poses a significant threat to the banking industry, with fraudsters continually evolving their tactics to exploit vulnerabilities. This paper investigates the efficacy of various machine learning algorithms for fraud detection using the Credit Card Fraud dataset from Kaggle. The paper explores Decision Tree, K-Nearest Neighbors (KNN), Logistic Regression, Support Vector Machine (SVM), Random Forest, and XGBoost algorithms. The study analyzes the performance of these models and discusses their real-time implementation in banking systems. Furthermore, we outline potential future directions to enhance fraud detection capabilities.